Mohammad Yaqub

Evaluation and Comparison of Current Fetal Ultrasound Image Segmentation Methods for Biometric Measurements: A Grand Challenge

This paper presents the evaluation results of the methods submitted to Challenge US: Biometric Measurements from Fetal Ultrasound Images, a segmentation challenge held at the IEEE International Symposium on Biomedical Imaging 2012. The challenge was set to compare and evaluate current fetal ultrasound image segmentation methods. It consisted of automatically segmenting fetal anatomical structures to measure standard obstetric biometric parameters, from 2D fetal ultrasound images taken on fetuses at different gestational ages (21 weeks, 28 weeks, and 33 weeks) and with varying image quality to reflect data encountered in real clinical environments. Four independent sub-challenges were proposed, according to the objects of interest measured in clinical practice: abdomen, head, femur, and whole fetus. Five teams participated in the head sub-challenge and two teams in the femur sub-challenge, including one team who tackled both. Nobody attempted the abdomen and whole fetus sub-challenges. The challenge goals were two-fold and the participants were asked to submit the segmentation results as well as the measurements derived from the segmented objects. Extensive quantitative (region-based, distance-based, and Bland-Altman measurements) and qualitative evaluation was performed to compare the results from a representative selection of current methods submitted to the challenge. Several experts (three for the head sub-challenge and two for the femur sub-challenge), with different degrees of expertise, manually delineated the objects of interest to define the ground truth used within the evaluation framework. For the head sub-challenge, several groups produced results that could be potentially used in clinical settings, with comparable performance to manual delineations. The femur sub-challenge had inferior performance to the head sub-challenge due to the fact that it is a harder segmentation problem and that the techniques presented relied more on the femurs appearance.

Investigation of the Role of Feature Selection and Weighted Voting in Random Forests for 3-D Volumetric Segmentation

This paper describes a novel 3-D segmentation technique posed within the Random Forests (RF) classification framework. Two improvements over the traditional RF framework are considered. Motivated by the high redundancy of feature selection in the traditional RF framework, the first contribution develops methods to improve voxel classification by selecting relatively “strong” features and neglecting “weak” ones. The second contribution involves weighting each tree in the forest during the testing stage, to provide an unbiased and more accurate decision than provided by the traditional RF. To demonstrate the improvement achieved by these enhancements, experimental validation is performed on adult brain MRI and 3-D fetal femoral ultrasound datasets. In a comparison of the new method with a traditional Random Forest, the new method showed a notable improvement in segmentation accuracy. We also compared the new method with other state-of-the-art techniques to place it in context of the current 3-D medical image segmentation literature.

Learning-based prediction of gestational age from ultrasound images of the fetal brain

Graphical abstract

Guided Random Forests for Identification of Key Fetal Anatomy and Image Categorization in Ultrasound Scans

In this paper, we propose a novel machine learning based method to categorize unlabeled fetal ultrasound images. The proposed method guides the learning of a Random Forests classifier to extract features from regions inside the images where meaningful structures exist. The new method utilizes a translation and orientation invariant feature which captures the appearance of a region at multiple spatial resolutions. Evaluated on a large real world clinical dataset (~30K images from a hospital database), our method showed very promising categorization accuracy (accuracytop1 is 75% while accuracytop2 is 91%).

Class-Specific Regression Random Forest for Accurate Extraction of Standard Planes from 3D Echocardiography

This paper proposes a class-specific regression random forest as a fully automatic algorithm for extraction of the standard view planes from 3D echocardiography. We present a natural, continuous parameterization of the plane detection task and address it by the regression voting algorithm. We integrate the voxel class label information into the training of the regression forest to exclude irrelevant classes from voting. This yields a class-specific regression forest. Two objective functions are employed to optimize for both the class label and the class-conditional regression parameters. During testing, high uncertainty class-specific predictors are excluded from voting, maximizing the confidence of the continuous output predictions.

Plane Localization in 3-D Fetal Neurosonography for Longitudinal Analysis of the Developing Brain

The parasagittal (PS) plane is a 2-D diagnostic plane used routinely in cranial ultrasonography of the neonatal brain. This paper develops a novel approach to find the PS plane in a 3-D fetal ultrasound scan to allow image-based biomarkers to be tracked from prebirth through the first weeks of postbirth life. We propose an accurate plane-finding solution based on regression forests (RF). The method initially localizes the fetal brain and its midline automatically. The midline on several axial slices is used to detect the midsagittal plane, which is used as a constraint in the proposed RF framework to detect the PS plane. The proposed learning algorithm guides the RF learning method in a novel way by: 1) using informative voxels and voxel informative strength as a weighting within the training stage objective function, and 2) introducing regularization of the RF by proposing a geometrical feature within the training stage. Results on clinical data indicate that the new automated method is more reproducible than manual plane finding obtained by two clinicians.

A Constrained Regression Forests Solution to 3D Fetal Ultrasound Plane Localization for Longitudinal Analysis of Brain Growth and Maturation

This paper develops a novel approach to find the plane in a 3D fetal ultrasound scan which corresponds to the 2D diagnostic plane used in cranial ultrasound of a neonate to allow image-based biomarkers to be tracked from pre-birth through the first weeks of post-birth life. We propose a method based on regression forests (RF) with important algorithm design considerations taken into account to provide an accurate plane-finding solution. Specifically, the new method constrains the RF method by 1) using informative voxels and voxel informative strength as a weighting within the training stage objective function u, and 2) introducing regularization of the RF by proposing a geometrical feature within the training stage. Results on clinical data indicate that the new automated method is more reproducible than manual plane finding.

Surface area measurement using rendered three‐dimensional ultrasound imaging: an in‐vitro phantom study

Cranial sutures and fontanelles can be reliably demonstrated using three‐dimensional (3D) ultrasound with rendering. Our objective was to assess the repeatability and validity of fontanelle surface area measurement on rendered 3D images.

Fully-automated alignment of 3D fetal brain ultrasound to a canonical reference space using multi-task learning.

HIGHLIGHTSWe propose a FCN to automatically co‐align 3D fetal neurosonography images.The multi‐task FCN predicts skull boundaries, eye location, and 3D brain orientation.Our proposed brain alignment method is invariant to fetal size and gestational age.Structural and anatomical correspondence was achieved in 88% of 140 tested volumes. ABSTRACT Methods for aligning 3D fetal neurosonography images must be robust to (i) intensity variations, (ii) anatomical and age‐specific differences within the fetal population, and (iii) the variations in fetal position. To this end, we propose a multi‐task fully convolutional neural network (FCN) architecture to address the problem of 3D fetal brain localization, structural segmentation, and alignment to a referential coordinate system. Instead of treating these tasks as independent problems, we optimize the network by simultaneously learning features shared within the input data pertaining to the correlated tasks, and later branching out into task‐specific output streams. Brain alignment is achieved by defining a parametric coordinate system based on skull boundaries, location of the eye sockets, and head pose, as predicted from intracranial structures. This information is used to estimate an affine transformation to align a volumetric image to the skull‐based coordinate system. Co‐alignment of 140 fetal ultrasound volumes (age range: 26.0±4.4 weeks) was achieved with high brain overlap and low eye localization error, regardless of gestational age or head size. The automatically co‐aligned volumes show good structural correspondence between fetal anatomies.

Volumetric Segmentation of Key Fetal Brain Structures in 3D Ultrasound

Neurosonography is the most widely used imaging technique for assessing neuro-development of the growing fetus in clinical practice. 3D neurosonography has an advantage of quick acquisition but is yet to demonstrate improvements in clinical workflow. In this paper we propose an automatic technique to segment four important fetal brain structures in 3D ultrasound. The technique is built within a Random Decision Forests framework. Our solution includes novel pre-processing and new features. The pre-processing step makes sure that all volumes are in the same coordinate. The new features constrain the appearance framework by adding a novel distance feature. Validation on 51 3D fetal neurosonography images shows that the proposed technique is capable of segmenting fetal brain structures and providing promising qualitative and quantitative results.